Abstract: In one embodiment, an apparatus comprises a storage device comprising a NAND flash memory. The storage device is to store a first page of data in a plurality of cells of the NAND flash memory in a first programming pass; and preserve the readability of the first page of data in the plurality of cells during a subsequent programming pass comprising a plurality of program loops, at least one of the plurality of program loops to comprise application of a first voltage to a first group of cells of the plurality of cells and application of a second voltage to a second group of cells of the plurality of cells, wherein the first group comprises cells that were not programmed in the first programming pass and the second group comprises cells that were programmed in the first programming pass.

Abstract: Methods and apparatus related to predictive Count Fail Byte (CFBYTE) for non-volatile memory are described. In one embodiment, logic determines a number of memory cells of the non-volatile memory that would pass or fail verification in a current program loop. The logic determines the number of the memory cells based at least in part on information from a previous program loop. The previous program loop is executed prior to the current program loop. The logic causes inhibition of one or more verification pulses to be issued in the current program loop based on comparison of the information from the previous program loop and a threshold value. Other embodiments are also disclosed and claimed.

Abstract: Technology for programming a page of memory in a NAND memory device is disclosed and described. In an example, a method includes applying initial programming pulses for lower page programming of the page and pre-reading data of the lower page. The method also includes determining whether to apply an error recovery operation to the data of the lower page. Data indicative of secondary programming pulses to be used for programming upper page data are stored and the upper page data is programmed based on the secondary programming pulses and the data of the lower page.

Abstract: Methods, apparatus, systems and articles of manufacture to preserve data of a solid state drive during a power loss event are disclosed. An example method includes setting an alternate data cache (PDC1) to a logical AND of a secondary data cache (SDC) and a primary data cache (PDC0). The PDC1 is set to a logical AND of the PDC1 and a first result of a first sense operation. The PDC0 is set to a logical AND of the PDC0 and an inverse value of the PDC1. The PDC1 is set to a logical AND of the SDC and the PDC0. The PDC1 is set to a logical AND of the PDC1 and an inverse value of a second result of a second sense operation. The SDC is set to a logical AND of the SDC and the PDC0. The SDC is set to a logical OR of the SDC or the PDC0. The PDC0 is set to a logical AND of the PDC0 and a third result of a third sensing operation.

Abstract: Apparatuses and methods for performing concurrent memory access operations for multiple memory planes are disclosed herein. An example method may include receiving first and second command and address pairs associated with first and second plane, respectively, of a memory. The method may further include, responsive to receiving the first and second command and address pairs, providing a first and second read voltages based on first and second page type determined from the first and second command and address pair. The method may further include configuring a first GAL decoder circuit to provide one of the first read voltage or a pass voltage on each GAL of a first GAL bus. The method may further include configuring a second GAL decoder circuit to provide one of the second read level voltage signal or the pass voltage signal on each GAL of a second GAL bus coupled to the second memory plane.

Abstract: Technology for an apparatus is described. The apparatus can include a first non-volatile memory, a second non-volatile memory to have a write access time faster than the first non-volatile memory, and a memory controller. The memory controller can be configured to detect corrupted data in a selected data region in the first non-volatile memory. The selected data region can be associated with an increased risk of data corruption after data is written from the second non-volatile memory to the first non-volatile memory. Uncorrupted data in the second non-volatile memory that corresponds to the corrupted data in the first non-volatile memory can be identified. Data recovery in the first non-volatile memory can be performed by replacing the corrupted data in the first non-volatile memory with uncorrupted data from the second non-volatile memory.

Abstract: Systems, apparatuses and methods may provide for identifying a target sub-block of NAND strings to be partially or wholly erased in memory and triggering a leakage current condition in one or more target select gate drain-side (SGD) devices associated with the target sub-block. Additionally, the leakage current condition may be inhibited in one or more remaining SGD devices associated with remaining sub-blocks of NAND strings in the memory. In one example, triggering the leakage current condition in the one or more target SGD devices includes setting a gate voltage of the one or more target SGD devices to a value that generates a reverse voltage that exceeds a threshold corresponding to the leakage current condition.

Abstract: Examples may include techniques to recover data from a solid state drive (SSD) using exclusive OR (XOR) parity information. Data saved to non-volatile types of block-erasable memory such as NAND memory included in the SSD may be recovered via use of XOR parity information saved to types of write-in-place memory such as a 3-dimensional cross-point memory also included in the SSD.

Abstract: In a memory device, odd bit lines of a flag memory cell array are connected with a short circuit to a dynamic data cache. Even bit lines of the flag memory cell array are disconnected from the dynamic data cache. When an even page of a main memory cell array is read, the odd flag memory cells, comprising flag data, are read at the same time so that it can be determined whether the odd page of the main memory cell array has been programmed. If the flag data indicates that the odd page has not been programmed, threshold voltage windows can be adjusted to determine the states of the sensed even memory cell page.

Abstract: Techniques are disclosed for programming memory devices such as solid-state drives. In an embodiment, a memory controller is configured to execute a programming sequence that interleaves coarse and fine tuning steps for neighboring word lines. In one example, three consecutive word lines are programmed in six steps. At step 1, word line n is coarse programmed to an intermediate voltage level; at step 2, word line n+1 is coarse programmed to an intermediate voltage level; at step 3, word line n is fine programmed to its target voltage level; at step 4, word line n+2 is coarse programmed to an intermediate voltage level; at step 5, word line n+1 is fine programmed to its target voltage level; at step 6, word line n+2 is fine programmed to its target voltage level. No reads are allowed until all cell levels are programmed. Phase change memory may be used as staging buffer.

Abstract: This disclosure concerns memory cell sensing. One or more methods include determining a data state of a first memory cell coupled to a first data line, determining a data state of a third memory cell coupled to a third data line, transferring determined data of at least one of the first and the third memory cells to a data line control unit corresponding to a second data line to which a second memory cell is coupled, the second data line being adjacent to the first data line and the third data line, and determining a data state of the second memory cell based, at least partially, on the transferred determined data.

Abstract: Methods, apparatus, systems and articles of manufacture to preserve data of a solid state drive during a power loss event are disclosed. An example method includes sending, upon detection of the power loss event, from a processor of the solid state drive, a command to abort an ongoing write operation of an aborted memory cell. In response to an indication that the ongoing write operation is aborted, the data to be written to the aborted memory cell is recovered. A first portion of the data to be written to the aborted memory cell is written to a first memory cell. A second portion of the data to be written to the aborted memory cell is written to a second memory cell.

Abstract: Systems and methods of managing defects in nonvolatile storage systems that can be used to avoid an inadvertent loss of data, while maintaining as much useful memory in the nonvolatile storage systems as possible. The disclosed systems and methods can monitor a plurality of trigger events for detecting possible defects in one or more nonvolatile memory (NVM) devices included in the nonvolatile storage systems, and apply one or more defect management policies to the respective NVM devices based on the types of trigger events that resulted in detection of the possible defects. Such defect management policies can be used proactively to retire memory in the nonvolatile storage systems with increased granularity, focusing the retirement of memory on regions of nonvolatile memory that are likely to contain a defect.

Abstract: The inhibit voltage is a voltage applied to wordlines adjacent to a program wordline having a memory cell to write during the program operation. The inhibit voltage for a program operation can be ramped up during the program pulse. Instead of applying a constant high inhibit voltage that results in the initial boosted channel potential reducing drastically due to leakage, a system can start the inhibit voltage lower and ramp the inhibit voltage up during the program pulse. The ramping up can be a continuous ramp or in finite discrete steps during the program pulse. Such ramping of inhibit voltage can provide better tradeoff between program disturb and inhibit disturb.

Abstract: Memory devices, methods for programming sense flags, methods for sensing flags, and memory systems are disclosed. In one such memory device, the odd bit lines of a flag memory cell array are connected with a short circuit to a dynamic data cache. The even bit lines of the flag memory cell array are disconnected from the dynamic data cache. When an even page of a main memory cell array is read, the odd flag memory cells, comprising flag data, are read at the same time so that it can be determined whether the odd page of the main memory cell array has been programmed. If the flag data indicates that the odd page has not been programmed, threshold voltage windows can be adjusted to determine the states of the sensed even memory cell page.

Abstract: Methods, and apparatuses to erase and or soft program a block of NAND memory may include performing an erase cycle on a block of NAND memory comprising two or more sub-blocks, verifying the two or more sub-blocks until a sub-block fails to verify, stopping the verification in response to the failed verify, performing another erase cycle on the block of NAND memory, and re-starting to verify the two or more sub-blocks at the sub-block that failed to verify

Abstract: Methods of programming memories include applying a first plurality of programming pulses to the group of memory cells to program first data to the group of memory cells, determining an upper limit of a resulting threshold voltage distribution for the group of memory cells following a particular programming pulse of the first plurality of programming pulses, and applying a second plurality of programming pulses to the group of memory cells to program second data to the group of memory cells, wherein a characteristic of at least one of the programming pulses of the second plurality of programming pulses is at least partially based on the determined upper limit of the threshold voltage distribution. Methods of programming memories further include programming information indicative of usage of memory cells of a page of memory cells to the page of memory cells during a portion of a programming operation.

Abstract: Methods of operating a memory include applying a multi-step pass voltage to a plurality of memory cells selected for a programming operation, applying a programming pulse to the plurality of memory cells selected for the programming operation after applying a voltage level of a particular step of the multi-step pass voltage to the plurality of memory cells selected for the programming operation, applying a particular voltage level to any data lines coupled to a first subset of memory cells of the plurality of memory cells selected for the programming operation prior to applying a voltage level of a certain step of the multi-step pass voltage, and applying the particular voltage level to any data lines coupled to a second subset of memory cells of the plurality of memory cells selected for the programming operation only after applying the voltage level of the certain step of the multi-step pass voltage.

Abstract: Described is a method which comprises performing a first read from a portion of a non-volatile memory, the first read to provide a first codeword; decoding the first codeword; determining whether the decoding operation failed; performing a second read from the portion of the non-volatile memory when it is determined that the decoding operation failed, the second read to provide a second codeword; and decoding the second codeword with an errors-and-erasures decoding process.

Abstract: The inhibit voltage is a voltage applied to wordlines adjacent to a program wordline having a memory cell to write during the program operation. The inhibit voltage for a program operation can be ramped up during the program pulse. Instead of applying a constant high inhibit voltage that results in the initial boosted channel potential reducing drastically due to leakage, a system can start the inhibit voltage lower and ramp the inhibit voltage up during the program pulse. The ramping up can be a continuous ramp or in finite discrete steps during the program pulse. Such ramping of inhibit voltage can provide better tradeoff between program disturb and inhibit disturb.